Your agent can do more. Find the skill that makes it happen.
Find your next superpower If you are an agent, refer to our llms.txt for full access."..." for exact phrases · Try typography, debugging or spreadsheetProvides templates and structured approaches for documenting codebases. Covers getting-started guides, project structure, architecture, code comments, and API documentation for new developers.
Quickly understand an unfamiliar codebase or project by mapping its architecture, identifying key components and data flows, and surfacing complexity hotspots. Load when the user asks to understand a repo, explain how something works, map the architecture, onboard to a codebase, or explore how components connect. Also triggers on "walk me through this codebase", "how does this project work", "expl…
Leverage the GitNexus knowledge graph and call traces to understand codebase structure, execution flows, symbol dependencies, and blast radius. Trigger with "understand codebase", "trace call flow", "impact analysis", "what calls X", or when navigating unfamiliar code architectures.
Provides guidance for @json-render/codegen utilities. Covers code generation from UI specs, custom exporters, specification traversal, and prop serialization.
AI 자율 개발 루프 제어 스킬. codeloop start/stop/status 서브커맨드로 Stop Hook 기반 무한 루프를 시작·중지·모니터링한다. Triggers: codeloop, codeloop start, codeloop stop, codeloop status, 루프 시작, 루프 중지, 루프 상태, ループ開始, ループ停止, 循环启动
Guides CodeQL security analysis setup through GitHub Actions workflows and CLI commands. Covers scanning configuration, SARIF output, and troubleshooting analysis issues.
Runs interprocedural CodeQL security analysis across supported languages. Offers broad or high-precision scan modes and creates data extension models for project-specific sources and sinks.
Defines a blank-canvas interface with almost no color and typography carrying the visual weight. Uses black for filled elements, dividers, and card surfaces.
OpenAI Codex CLI wrapper — three modes. (gstack)
Provides Codex CLI delegation workflows using GPT-5.3-codex models for code generation, refactoring, and architectural analysis. Covers English prompts, execution flags, sandbox modes, and safe result handling.
Supports running Codex CLI commands such as codex exec and codex resume for software engineering tasks. Covers code analysis, refactoring, and automated edits, with GPT-5.2 specified as its default model.
Uses codex_app tools to create, inspect, message, wait on, fork, rename, archive, and pin threads. Also manages automations, reminders, and navigation in sessions using custom non-OpenAI models.
A growing collection of real, public skills. Descriptions and instructions indexed 25 Sept 2026.
Skills give your agent reusable instructions for a specific job. Pick one, read what it does, and bring it into your workflow.
A name only tells half the story. Search the full description and instructions to find the right fit.
Read the skill, visit its source, and see exactly what you’re adding to your agent.
Copy the install command from a skill page and run it in your project.
npx skillycli add owner/repo --skill name